A Survey on CDPCF: Concise Discriminative Patterns Based Classification Framework

Abstract:   Example based arrangement was initially proposed to enhance the precision utilizing chosen visit designs, where numerous endeavours were paid to prune a colossal number of non-discriminative successive examples. Then again, tree-based models have demonstrated solid capacities on numerous arrangement errands since they can undoubtedly fabricate high-arrange communications between various highlights and furthermore handle both numerical and downright highlights and high dimensional highlights. Simple models such as generalized linear models have ordinary performance but strong interpretability on a set of simple features. There are different series which includes tree-based models, organize numerical, categorical and high dimensional features into a comprehensive structure with rich interpretable information in the data. Frequent pattern-based classification methods have shown to be very effective at classifying categorical or high dimensional sparse datasets

Keywords: Discriminative pattern, Tree based model